Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 108 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1179459 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0323. Min Act: -0.0006

Data Index: 879145 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1002185 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1297936 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0302. Min Act: -0.0006

Data Index: 236487 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0286. Min Act: -0.0006

Data Index: 84131 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0327. Min Act: -0.0006

Data Index: 150126 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0309. Min Act: -0.0006

Data Index: 34994 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0292. Min Act: -0.0006

Data Index: 22094 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0297. Min Act: -0.0006

Data Index: 62658 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0297. Min Act: -0.0006

Data Index: 193605 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0303. Min Act: -0.0006

Data Index: 737256 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0299. Min Act: -0.0006

Data Index: 142911 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0262. Min Act: -0.0006

Data Index: 268734 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0291. Min Act: -0.0006

Data Index: 764370 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0272. Min Act: -0.0006

Data Index: 789490 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1322542 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0302. Min Act: -0.0006

Data Index: 302266 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0260. Min Act: -0.0006

Data Index: 582713 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1231959 (C4 (Web Text))

Max Activating Token Index: 365